English(EN) 📊 Exaone 4.0 1.2B (Non-reasoning) — the actual numbers GPQA: 42.4% MMLU-Pro: 50% Humanity's Last Exam: 5.7% Long Context Reasoning: 0% Measured independently, n

Exaone 4.0 基准测试结果喜忧参半，推理能力得分较低

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-15 00:00

Exaone 4.0 是一个拥有 12 亿参数的模型，在多个基准测试中展示了特定的性能指标。独立测量的结果显示，它在 GPQA 上 đạt 42.4%，在 MMLU-Pro 上 đạt 50%，在 Humanity's Last Exam 上 đạt 5.7%。该模型在长上下文推理任务上的得分为 0%。 AI

影响提供了 Exaone 4.0 模型在关键基准测试中的具体性能数据，突出了其在推理方面的局限性。

排序理由该项目报告了特定模型的基准测试结果，属于研究范畴。[lever_c 从研究降级：ic=1 ai=1.0]

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 10 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该项目报告了特定模型的基准测试结果，属于研究范畴。[lever_c 从研究降级：ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: model release, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

Mastodon — mastodon.social TIER_1 English(EN) · opensourceaitech · 2026-10-15 00:00

📊 Exaone 4.0 1.2B（非推理）— 实际数字 GPQA：42.4% MMLU-Pro：50% 人类最后考试：5.7% 长上下文推理：0% 独立测量，n

📊 Exaone 4.0 1.2B (Non-reasoning) — the actual numbers GPQA: 42.4% MMLU-Pro: 50% Humanity's Last Exam: 5.7% Long Context Reasoning: 0% Measured independently, not self-reported → https:// olud.ai/leaderboard.html # LLM # Benchmarks # OpenSource # AI

链接 olud.ai/leaderboard.html

本文如何被排名

报道来源 [1]

📊 Exaone 4.0 1.2B（非推理）— 实际数字 GPQA：42.4% MMLU-Pro：50% 人类最后考试：5.7% 长上下文推理：0% 独立测量，n

相关实体

相关话题